Enter a domain. StackResolve probes every agent-readiness signal and returns a 0-100 AgentReady Score with a per-dimension breakdown in about 30 seconds. No login to try.
Can an agent find the product at all: registry presence, llms.txt, sitemap, search visibility.
Can it read the product: clear docs, an OpenAPI spec, structured output, described auth.
Can it install and call it unattended: MCP server, CLI, quickstart, no human-only steps.
Does it keep working: stable endpoints, error clarity, rate-limit headers, uptime.
The same audit runs over MCP, the CLI, or the REST API. One call in, a scored breakdown out.
// MCP tool call (hosted at stackresolve.dev/mcp)
audit({ domain: "firecrawl.dev" }){
"domain": "firecrawl.dev",
"scores": { "agentready": 96, "discovery": 94,
"understanding": 98, "adoption": 97, "operability": 95 },
"issues": [
"No rate-limit headers on 2 of 9 endpoints"
]
}Research returns structured, cited company facts from the same fact database.